org.kramerlab.autoencoder.neuralnet

FullBipartiteConnection

class FullBipartiteConnection extends MatrixParameterizedLayer with Serializable

Full bipartite graph between two layers with edges labeled by matrix entries of the weight matrix. The weight matrix has the width equal to the dimension of the output, and 'height' equal to the dimension of the input.

Linear Supertypes
MatrixParameterizedLayer, Serializable, Serializable, Layer, Visualizable, VectorSpace[Layer], AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. FullBipartiteConnection
  2. MatrixParameterizedLayer
  3. Serializable
  4. Serializable
  5. Layer
  6. Visualizable
  7. VectorSpace
  8. AnyRef
  9. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new FullBipartiteConnection(inputDim: Int, outputDim: Int)

  2. new FullBipartiteConnection(weights: Mat)

Value Members

  1. final def !=(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

    Definition Classes
    AnyRef → Any
  4. def *(d: Double): MatrixParameterizedLayer

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  5. def +(other: Layer): MatrixParameterizedLayer

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  6. def -(other: Layer): MatrixParameterizedLayer

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  7. def /(d: Double): MatrixParameterizedLayer

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  8. final def ==(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  9. final def ==(arg0: Any): Boolean

    Definition Classes
    Any
  10. def activityColorscheme: (Double) ⇒ Int

    Color map for the activities

    Color map for the activities

    Definition Classes
    Layer
  11. def activityShape: Option[(Int, Int)]

    Optionally, one can specify how to reshape the neuron activities for visualization (height, width).

    Optionally, one can specify how to reshape the neuron activities for visualization (height, width).

    Definition Classes
    Layer
  12. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  13. def build(newParams: Mat): FullBipartiteConnection

  14. var cachedInput: Mat

    Attributes
    protected
  15. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  16. def copy: FullBipartiteConnection

  17. def dot(other: Layer): Double

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  18. final def eq(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  19. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any
  20. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  21. final def getClass(): Class[_]

    Definition Classes
    AnyRef → Any
  22. def gradAndBackpropagationError(backpropagatedError: Mat): (FullBipartiteConnection, Mat)

    Returns the gradient (Layer-valued) and the backpropagated error, which is passed to the layer below.

    Returns the gradient (Layer-valued) and the backpropagated error, which is passed to the layer below.

    This method can rely on the fact that the propagate method already has been called in the first pass.

    backpropagatedError

    error propagated from above, formatted the same way (one row for each example) as input and output

    returns

    gradient (Layer-valued) and the next backpropagated error

    Definition Classes
    FullBipartiteConnectionLayer
  23. def hashCode(): Int

    Definition Classes
    AnyRef → Any
  24. val inputDimension: Int

    Definition Classes
    FullBipartiteConnectionLayer
  25. def isInfinite: Boolean

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  26. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any
  27. def isInvalid: Boolean

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  28. def isNaN: Boolean

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  29. final def ne(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  30. def norm: Double

    Definition Classes
    VectorSpace
  31. def normSq: Double

    Definition Classes
    VectorSpace
  32. def normalized: Layer

    Definition Classes
    VectorSpace
  33. final def notify(): Unit

    Definition Classes
    AnyRef
  34. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  35. val outputDimension: Int

    Definition Classes
    FullBipartiteConnectionLayer
  36. val parameters: Mat

    Definition Classes
    MatrixParameterizedLayer
  37. def propagate(input: Mat): Mat

    Returns the output given the input.

    Returns the output given the input. This method can cache data that could be useful on the second pass of the backpropagation.

    The input contains one example in each row, the output shall have the same layout.

    Definition Classes
    FullBipartiteConnectionLayer
  38. def reinitialize(weightScale: Double): FullBipartiteConnection

  39. def reverseLayer: FullBipartiteConnection

    Creates a new independent layer that has the same type as this one, but propagates the information in reverse direction

    Creates a new independent layer that has the same type as this one, but propagates the information in reverse direction

    Definition Classes
    FullBipartiteConnectionLayer
  40. def reversePropagate(output: Mat): Mat

    Returns the result of signal propagation in reverse direction

    Returns the result of signal propagation in reverse direction

    Definition Classes
    FullBipartiteConnectionLayer
  41. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef
  42. def toImage: BufferedImage

    Definition Classes
    MatrixParameterizedLayerVisualizable
  43. def toImage(w: Int, h: Int): BufferedImage

    Definition Classes
    Visualizable
  44. def toImage(colormap: (Double) ⇒ Int): BufferedImage

    Definition Classes
    Visualizable
  45. def toString(): String

    Definition Classes
    FullBipartiteConnection → AnyRef → Any
  46. def unary_-: MatrixParameterizedLayer

    Definition Classes
    MatrixParameterizedLayerVectorSpace
  47. def visualizeActivity(activity: Mat): BufferedImage

    Definition Classes
    Layer
  48. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  49. final def wait(arg0: Long, arg1: Int): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  50. final def wait(arg0: Long): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  51. def zero: MatrixParameterizedLayer

    Definition Classes
    MatrixParameterizedLayerVectorSpace

Inherited from MatrixParameterizedLayer

Inherited from Serializable

Inherited from Serializable

Inherited from Layer

Inherited from Visualizable

Inherited from VectorSpace[Layer]

Inherited from AnyRef

Inherited from Any

Ungrouped